| Abstract | Effectively selling products online is a challenging task. Today’s product domains often contain a dizzying variety of brands and models with highly complex sets of characteristics. Electronic products such as laptop computers, digital cameras, and mobile phones are good examples. This thesis addresses the problem of supporting utilitarian shopping in product domains containing large numbers of alternatives with complex sets of features. We can think of a utilitarian shopping as the process of searching for a product that best fits the shopper’s preference criteria. The process of choosing an outcome that best satisfies a set of preferences has been extensively studied in the field of Multi-¬Attribute Utility Theory (MAUT). The traditional MAUT approach to preference elicitation starts by describing each item in the choice set in terms of a number of attributes. The decision maker (the customer in this case) is then asked a series of questions concerning his preferences for various values of the attributes, as well as combinations of values. From the answers to these questions a preference order over the items is constructed and the most preferred item is recommended. The value of this approach is that it reduces the daunting task of choosing among a large set of complex alternatives to the process of answering a series of relatively simple questions. A number of online shopping websites provide product choice assistance by directly implementing this procedure. Examples are Active Buyers Guide and General Motors’ vehicle advisor. While this approach is appealing due to its solid theoretical foundations, there are several reasons that it does not fit well with people’s decision making behavior. From the standpoint of shopping behavior, it is rather off putting for a customer to be forced to answer a long series of questions before he is permitted to see the list of available products. More generally, more recent research in the area of behavioral decision theory indicates that human choice is an adaptive and constructive process rather than one of expressing existing well-defined preferences. This has a number of implications for product choice assistance tools. This dissertation presents a system that addresses all these issues. The system is called VMAP for Visualizing Multi-attribute Preferences. VMAP provides on one screen both a multi-attribute preference tool (MAP-Tool) and a product visualization tool (V-Tool). The product visualization tool displays the set of available products, with each product displayed as a point in a 3-D attribute space. By viewing the product space, users can gain an overview of the range of available products, as well as an understanding of the relationships between their attributes. The MAP-Tool integrates expression of preferences and filter conditions, which are then immediately reflected in the V-Tool display. In this way, the user can immediately see the consequences of his expressed preferences on the product space. By including the entire preference elicitation interface in one screen, the user can easily specify preferences in any order and change earlier expressed preferences. The proposed system was evaluated to determine the benefit gained by combining visualization with MAUT versus the use of MAUT alone. First a questionnaire was designed and tested. Then a group of participants was recruited and each participant was asked to perform a series of tasks using VMAP and using a more traditional MAUT product selection tool. Participants were then asked to rate each system according to a variety of criteria such as ease of use, speed of use, confidence in the result, and the extent to which the tool helped the user to understand the product domain. The results show that while VMAP is somewhat more difficult to use than a traditional MAUT product selection tool, it provides better flexibility, provides the ability to more effectively explore the product domain, and produces more confidence in the selected product. |